CN112652400A - Method, system, device and medium for reference of disease condition based on special disease view similarity analysis - Google Patents
Method, system, device and medium for reference of disease condition based on special disease view similarity analysis Download PDFInfo
- Publication number
- CN112652400A CN112652400A CN202011486411.8A CN202011486411A CN112652400A CN 112652400 A CN112652400 A CN 112652400A CN 202011486411 A CN202011486411 A CN 202011486411A CN 112652400 A CN112652400 A CN 112652400A
- Authority
- CN
- China
- Prior art keywords
- patient
- similar
- disease
- patients
- similar patients
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/50—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for simulation or modelling of medical disorders
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a reference method, a system, equipment and a medium for analyzing disease conditions based on special disease view similarity, wherein the reference method comprises the following steps: acquiring similar patients from a patient database according to the index of the target patient to form a similar patient pool; and acquiring a disease baseline reference value according to similar patients. The invention realizes the evaluation of the state of an illness and the observation of the development trend through the simulation of the state of an illness of a patient based on a disease-specific view according to the type of the illness, provides the comparison with the actual development condition, and carries out risk notification and diagnosis and treatment scheme suggestion according to the comparison result, thereby realizing the clinical evaluation, risk prejudgment and auxiliary diagnosis and treatment decision on the development trend of the state of an illness of the patient, and further improving the clinical curative effect, quality safety and operation efficiency.
Description
Technical Field
The invention relates to the technical field of special disease view similarity analysis, in particular to a disease condition reference method, system, equipment and medium based on special disease view similarity analysis.
Background
With the continuous acceleration of the process of Medical informatization, the informatization System of the traditional Hospital is a plurality of independent diagnosis and treatment systems mainly including HIS (Hospital Information System), CIS (Clinical Information System), EMR (Electronic Medical Record), NIS (Nursing Information System), LIS (Laboratory Information Management System), RIS (Radiology Information Management System) and the like, and the Clinical diagnosis and treatment application is gradually developing and treating and using a Clinical data center as a core and integrating all Clinical data into a whole. At present, the construction of a clinical data center and the integrated display of data become mature day by day, so that doctors can comprehensively and quickly check and master the diagnosis and treatment information of patients.
The current special disease view shows the state of an illness of a patient according to the visual angle of the disease species and based on the clinical guideline of the special disease and the diagnosis and treatment path, the problem of quick browsing of the state of the illness of the patient is solved, and the requirement that different diagnosis and treatment contents are focused according to different visual angles in clinic is met. However, diagnosis and treatment of diseases are not developed as textbooks, each patient has its own characteristics and differences, and in the diagnosis and treatment process, besides according to a professional diagnosis and treatment guideline, the personal professional experience of a doctor and the cognitive degree of similar patients play an important role, which directly affects the diagnosis and treatment scheme of the patient and the degree of grasp of the disease trend.
The existing diagnosis and treatment view for the special diseases only objectively reflects the clinical data change of the patient and the display of the diagnosis and treatment scheme condition, and is the extraction, summarization and display of objective facts. However, no effective in-depth analysis and auxiliary clinical decision making are available for the patient condition trend analysis and the potential risk estimation.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the defect that the existing special disease diagnosis and treatment view only provides objective clinical data summary according to a clinical guide and a clinical path, and provides a disease condition reference method, a system, equipment and a medium based on special disease view similar analysis, which can perform comparative analysis and trend prediction on similar cases from a special disease view to assist clinical diagnosis and treatment decision.
The invention solves the technical problems through the following technical scheme:
the invention provides a disease condition reference method based on special disease view similarity analysis, which comprises the following steps:
acquiring similar patients from a patient database according to the index of the target patient to form a similar patient pool;
obtaining a disease baseline reference value according to similar patients.
Preferably, the step of retrieving similar patients from the patient database based on the target patient comprises:
and obtaining static similar patients according to the static indexes.
Preferably, the step of obtaining the statically similar patients according to the static index comprises:
acquiring a first matching degree of the historical patient and the target patient in a patient database, and setting the historical patient as a static similar patient if the first matching degree is greater than a preset threshold value;
first degree of matching S (X)i，Yj)＝∑kakS(Xik，Yjk)；
Wherein, XiCharacterization of the ith target patient, YjCharacterization of the jth historical patient, S (X)i，Yj) Characterization of XiAnd YjThe first degree of matching; xikCharacterization of the kth static index, Y, of the ith target patientjkCharacterization of the kth static index, S (X), for the jth historical patientik，Yjk) Characterization of XikA second degree of matching of the table; a iskRepresenting the information weight value, sigma, corresponding to the kth static indexkak＝1。
Preferably, the static indicators include at least one of age group, diagnosis name, treatment regimen.
Preferably, the step of retrieving similar patients from the patient database based on the target patient comprises:
and acquiring dynamic similar patients according to the dynamic indexes.
Preferably, the obtaining of dynamically similar patients according to the dynamic index includes:
acquiring dynamic similar patients from historical patients in a patient database according to the reference amount;
wherein, the reference amount is:
wherein n is a difference;
if the reference quantity is larger than the preset threshold value, setting the historical patient as a dynamic similar patient.
Preferably, the baseline reference value of the condition is obtained from at least one of the mean, median, mode, and confidence interval of the indicators of similar patients.
The invention also provides a disease condition reference system based on the special disease view similarity analysis, which comprises a similarity acquisition unit and a baseline acquisition unit;
the similar acquisition unit is used for acquiring similar patients from a patient database according to the indexes of the target patient to form a similar patient pool;
the baseline acquisition unit is used for acquiring a disease baseline reference value according to similar patients.
The invention also provides an electronic device which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the method for referring to the disease condition based on the special disease view similarity analysis is realized.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for reference of a medical condition based on a specific disease view similarity analysis of the present invention.
The positive progress effects of the invention are as follows: the invention realizes the development prediction of the disease condition through the disease condition simulation of the patient based on the disease-specific view according to the disease category, provides the comparison with the actual development condition, carries out risk assessment and suggestion on the predicted simulation result, further proposes and disposes the suggestion, realizes the clinical advance perception of the disease condition development of the patient, ensures that the risk of the patient makes countermeasures in advance and improves the effective rate of clinical diagnosis and treatment.
Drawings
FIG. 1 is a flowchart of a reference method for analyzing disease based on a spot-specific view similarity analysis according to example 1 of the present invention.
Fig. 2 is a schematic structural diagram of a disease reference system based on a special disease view similarity analysis according to embodiment 2 of the present invention.
Fig. 3 is a schematic structural diagram of an electronic device according to embodiment 3 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
The embodiment provides a disease condition reference method based on special disease view similarity analysis. Referring to fig. 1, the reference method includes the steps of:
and step S1, acquiring similar patients from the patient database according to the index of the target patient to form a similar patient pool.
And step S2, acquiring a disease baseline reference value according to similar patients.
The embodiment is mainly based on a disease species fuzzy matching mechanism in a disease-specific view, a historical similar patient pool is searched according to a target patient (namely a target for pre-evaluation of disease development), similar analysis is continuously performed on the change of the disease of relevant signs of the patient to form a similar patient matching engine, and meanwhile, the disease of the target patient is simulated according to the disease development trend of a cured patient.
The special disease category similarity analysis model based on a large amount of clinical medical data mining, like a large amount of existing case experiences, can directly help clinicians to carry out real-time dynamic similarity monitoring analysis in the hospitalization diagnosis and treatment process of patients, and finds the most similar case matching look-up and reference. Meanwhile, the disease trend of the patient is estimated according to the historical data of similar patients, and the data is used for analyzing the most appropriate treatment scheme, treatment result, possible hospitalization duration, expense consumption, prognosis survival and other conditions. The method has great positive significance for individual diagnosis and treatment effects of patients, clinical medical quality, medical resource consumption, operation efficiency improvement and the like.
Before similar patients are acquired, first, a patient database is constructed. When a patient database is constructed, preliminary data is obtained through a data acquisition mode. Then, structured data cleaning conversion, data preprocessing, NLP (Natural Language Processing), unstructured data structuring and the like are performed on the preliminary data to obtain a patient database for screening of similar patients. Operations such as structured data cleansing conversion, data preprocessing, NLP, unstructured data structuring, etc. are capable of being implemented by those skilled in the art and will not be described herein in detail.
In an alternative embodiment, the classification is performed according to the target patient registration department, and then, in step S1, the same diagnosis patient is obtained by screening in the patient database from the main diagnosis of the target patient. And finally, performing similar patient analysis according to the age, sex, basic physical signs, inspection indexes of the target patient, diagnosis, medical history, examination results, medication conditions and other indexes of the target patient, constructing a case similarity analysis engine, continuously optimizing the case similarity analysis engine through continuous increase of samples, and simultaneously removing irrelevant index factors, thereby obtaining a similar patient pool. This class of similar patients is referred to as "static similar patients" and the corresponding pool of similar patients is referred to as "static similar patient pool".
As an alternative embodiment, static similar patients are obtained based on the degree of matching. In specific implementation, by defining the importance degree of the basic information during matching, the matching degree of the patient information is defined as a weighted sum of the matching degrees of the fields, the maximum value of the weighted sum is 1, the minimum value of the weighted sum is 0, and the weighted formula of the matching degree is expressed as:
S(Xi，Yj)＝∑kakS(Xik，Yjk)；
in the formula, S (X)i，Yj) The matching degree of the ith piece of submitted information and the jth piece of compared information in the submitted information source domain X and the compared database Y is shown;
S(Xik，Yjk) Means 2 pieces of contrast information Xi，YjThe matching degree of the kth field;
akis the information weight value corresponding to the k field, the value can be adjusted according to the situation, but the maximum value is 1, namely sigmakak＝1。
S(Xik，Yjk) The matching mode of the field information is defined as follows: the same returns 1, completely different returns 0; the other fields are analogized in turn. And returning 0 for the field with missing information according to different conditions, and directly judging that the information is not matched if the number of the missing fields is too large.
In specific implementation, the information source domain X is submitted as a target patient library, wherein XiCharacterization of the ith target patient of the target patient pool, XikThe kth field characterizing the ith target patient (e.g., the age of the target patient), the number of fields being related to the number of indices used for the alignment.In an alternative embodiment, the indexes for comparison include the age, sex, basic signs, test indexes, diagnosis, medical history, examination results, medication status, and the like of the target patient, and each index corresponds to one field.
The compared database Y is a patient database, wherein YjCharacterizing the jth historical patient in the patient database, YjkA kth field characterizing a jth historic patient in the patient database (e.g., the age of the target patient).
Degree of matching S (X)i，Yj) Above a preset threshold, historical patient YjIs a target patient XiSimilar patients as described above. By analogy, each target patient is matched and judged with the historical patients in the patient database one by one, so that all static similar patients are obtained, and a static similar patient pool is formed. That is, comparing the target patient with the historical patients one by one, the current index data is highly similar to the historical patients, such as: and if the process indexes such as age group, diagnosis name, treatment scheme and the like are similar, identifying the historical patient as a similar patient, and finally forming a similar patient pool.
In order to obtain a more accurate matching result, the case report physical sign report is unstructured and is matched after being structured. The specific implementation of the structuring is within the reach of the person skilled in the art and will not be described in detail here.
As an alternative embodiment, the similar patients further include dynamic similar patients. Dynamically similar patients are patients with similar index trends as historic patients (i.e., patients in the patient database). In step S1, the manner of acquiring dynamically similar patients is: and (4) performing similar judgment on the index development trends of the target patient and the historical patient, introducing a time trend dimension, and further performing item-by-item comparison. In specific implementation, 1, estimating the cost and the number of days of a target patient according to the hospitalization cost or the hospitalization days of the historical patient; 2. whether the target patient takes medicine or whether a certain operation is compared with the history of similar patients or not reaches the expected effect so as to judge whether the treatment scheme is effective or not.
In specific implementation, a similar patient set is obtained by collecting dynamic trends of target patients and historical patient indexes in a dynamic similarity matching mode, dynamic correlation analysis is carried out on the dynamic similarity matching process based on a time sequence, the dynamic similarity matching process is mainly represented by same trend fluctuation, the same trend fluctuation is similar to a time rising or falling trend line, and differences are generated due to dose or physique. As an alternative embodiment, the reference quantity is obtained by the following formula:
wherein n is a difference, T represents a time, XT、YTCharacterizing two patient index time series; x is the number oft、ytRespectively representing index data of a patient at a certain moment; by referencing the CORT, dynamically similar distances can be defined quantitatively, thus finding patients that are dynamically similar to the target patient. Such as: after a certain treatment scheme, the target patient has similarity of time fluctuation trends of indexes such as body temperature, heart rate, blood test, urine volume and the like.
After obtaining a pool of similar patients, a baseline reference value of the condition is generated for a set of similar patients based on case similarity analysis. The baseline reference value of the disease has guiding value for the treatment of the target patient.
Baseline reference values for the condition were obtained based on a similar patient set. In an alternative embodiment, in step S2, a baseline reference value for the condition is obtained based on one or more of the mean, median, mode, and confidence interval of the indices of similar patients. An estimation analysis of the target patient may also be performed by its time trend.
In an alternative embodiment, after the target patient (new patient to be treated) is admitted, according to the method for similarly analyzing the disease condition reference based on the special disease view of the present embodiment, similar patients are automatically found and a similar patient pool is formed according to the diagnosis, physical signs, test results, medication and other information of the target patient, a disease condition baseline reference value is obtained according to the similar patients, and changes of disease condition physical signs in the future 24 hours and 3 days are automatically estimated for the disease condition development of the target patient.
As a preferred embodiment, the baseline reference of the disease condition may also change simultaneously, with the change in the input data being based on real-time changes in the target patient as the disease condition progresses. That is, when the disease condition of the target patient progresses, similar patients are searched again from the patient database according to the current (i.e. changed) age, sex, basic physical signs, examination index, diagnosis, medical history, examination result, medication condition, etc. of the target patient. Based on the rolling and iterative search, the accuracy of searching similar patients can be improved, so that the disease development of the target patient can be estimated more accurately.
In other alternative embodiments, with a similar patient pool, the following functions may be implemented: estimating the change trend of the future illness, vital signs, various indexes of blood and the like; analyzing the effectiveness of the current patient treatment regimen according to historical patient treatment effects; estimating quantitative indexes such as patient cost, hospitalization days and the like; estimating risk assessment, such as nosocomial infection, fall pressure sores, venous thrombus delivery, etc.; and evaluating the effect of the treatment scheme.
Example 2
The embodiment provides a disease condition reference system based on special disease view similarity analysis. Referring to fig. 2, the reference system includes a similarity acquisition unit 201, a baseline acquisition unit 202; the similar acquiring unit 201 is used for acquiring similar patients from a patient database according to the indexes of the target patient to form a similar patient pool; the baseline acquisition unit 202 is used for acquiring a baseline reference value of the disease condition according to similar patients.
The embodiment is mainly based on a disease species fuzzy matching mechanism in a disease-specific view, a historical similar patient pool is searched according to a target patient (namely, an object for pre-estimation of disease condition development), similar analysis is continuously performed on the change of the disease condition of relevant signs of the patient to form a similar patient matching engine, and meanwhile, the disease condition of the target patient is simulated according to the disease condition development trend of a cured patient.
The special disease category similarity analysis model based on a large amount of clinical medical data mining, like a large amount of existing case experiences, can directly help clinicians to carry out real-time dynamic similarity monitoring analysis in the hospitalization diagnosis and treatment process of patients, and finds the most similar case matching look-up and reference. Meanwhile, the disease trend of the patient is estimated according to the historical data of similar patients, and the data is used for analyzing the most appropriate treatment scheme, treatment result, possible hospitalization duration, expense consumption, prognosis survival and other conditions. The method has great positive significance for individual diagnosis and treatment effects of patients, clinical medical quality, medical resource consumption, operation efficiency improvement and the like.
Before similar patients are acquired, first, a patient database is constructed. When a patient database is constructed, preliminary data is obtained through a data acquisition mode. And then, carrying out operations such as structured data cleaning conversion, data preprocessing, NLP, unstructured data structuring and the like on the primary data to obtain a patient database for screening similar patients. Operations such as structured data cleansing conversion, data preprocessing, NLP, unstructured data structuring, etc. are capable of being implemented by those skilled in the art and will not be described herein in detail.
In an alternative embodiment, the classification is performed according to the registered departments of the target patients, and then the similarity obtaining unit 201 obtains the same diagnosis patient by screening in the patient database from the main diagnosis of the target patient. And finally, performing similar patient analysis according to the age, sex, basic physical signs, inspection indexes of the target patient, diagnosis, medical history, examination results, medication conditions and other indexes of the target patient, constructing a case similarity analysis engine, continuously optimizing the case similarity analysis engine through continuous increase of samples, and simultaneously removing irrelevant index factors, thereby obtaining a similar patient pool. This class of similar patients is referred to as "static similar patients" and the corresponding pool of similar patients is referred to as "static similar patient pool".
As an alternative embodiment, the similarity obtaining unit 201 obtains a static similar patient based on the matching degree. In specific implementation, by defining the importance degree of the basic information during matching, the matching degree of the patient information is defined as a weighted sum of the matching degrees of the fields, the maximum value of the weighted sum is 1, the minimum value of the weighted sum is 0, and the weighted formula of the matching degree is expressed as:
S(Xi，Yj)＝∑kakS(Xik，Yjk)；
in the formula, S (X)i，Yj) The matching degree of the ith piece of submitted information and the jth piece of compared information in the submitted information source domain X and the compared database Y is shown;
S(Xik，Yjk) Means 2 pieces of contrast information Xi，YjThe matching degree of the kth field;
akis the information weight value corresponding to the k field, the value can be adjusted according to the situation, but the maximum value is 1, namely sigmakak＝1。
S(Xik，Yjk) The matching mode of the field information is defined as follows: the same returns 1, completely different returns 0; the other fields are analogized in turn. And returning 0 for the field with missing information according to different conditions, and directly judging that the information is not matched if the number of the missing fields is too large.
In specific implementation, the information source domain X is submitted as a target patient library, wherein XiCharacterization of the ith target patient of the target patient pool, XikThe kth field characterizing the ith target patient (e.g., the age of the target patient), the number of fields being related to the number of indices used for the alignment. In an alternative embodiment, the indexes for comparison include the age, sex, basic signs, test indexes, diagnosis, medical history, examination results, medication status, and the like of the target patient, and each index corresponds to one field.
The compared database Y is a patient database, wherein YjCharacterizing the jth historical patient in the patient database, YjkA kth field characterizing a jth historic patient in the patient database (e.g., the age of the target patient).
Degree of matching S (X)i，Yj) Above a preset threshold, historical patient YjIs a target patient XiSimilar patients as described above. By analogy, each target patient is matched and judged with the historical patients in the patient database one by one, so that the patient-based medical data management system is obtainedAnd forming a static similar patient pool by all static similar patients. That is, comparing the target patient with the historical patients one by one, the current index data is highly similar to the historical patients, such as: and if the process indexes such as age group, diagnosis name, treatment scheme and the like are similar, identifying the historical patient as a similar patient, and finally forming a similar patient pool.
In order to obtain a more accurate matching result, the case report physical sign report is unstructured and is matched after being structured. The specific implementation of the structuring is within the reach of the person skilled in the art and will not be described in detail here.
As an alternative embodiment, the similar patients further include dynamic similar patients. Dynamically similar patients are patients with similar index trends as historic patients (i.e., patients in the patient database). The manner in which the similar acquiring unit 201 acquires the dynamic similar patients is as follows: and (4) performing similar judgment on the index development trends of the target patient and the historical patient, introducing a time trend dimension, and further performing item-by-item comparison. In specific implementation, 1, estimating the cost and the number of days of a target patient according to the hospitalization cost or the hospitalization days of the historical patient; 2. whether the target patient takes medicine or whether a certain operation is compared with the history of similar patients or not reaches the expected effect so as to judge whether the treatment scheme is effective or not.
In specific implementation, a similar patient set is obtained by collecting dynamic trends of target patients and historical patient indexes in a dynamic similarity matching mode, dynamic correlation analysis is carried out on the dynamic similarity matching process based on a time sequence, the dynamic similarity matching process is mainly represented by same trend fluctuation, the same trend fluctuation is similar to a time rising or falling trend line, and differences are generated due to dose or physique. As an alternative embodiment, the reference quantity is obtained by the following formula:
wherein n is a difference, T represents a time, XT、YTCharacterizing two patient index time series; x is the number oft、ytRespectively representing index data of a patient at a certain moment; by referencing the CORT, dynamically similar distances can be defined quantitatively, thus finding patients that are dynamically similar to the target patient. Such as: after a certain treatment scheme, the target patient has similarity of time fluctuation trends of indexes such as body temperature, heart rate, blood test, urine volume and the like.
After obtaining a pool of similar patients, a baseline reference value of the condition is generated for a set of similar patients based on case similarity analysis. The baseline reference value of the disease has guiding value for the treatment of the target patient.
Baseline reference values for the condition were obtained based on a similar patient set. In an alternative embodiment, the baseline acquisition unit 202 obtains the baseline reference value of the disease condition according to one or more of the mean, median, mode, and confidence interval of the indicators of similar patients. An estimation analysis of the target patient may also be performed by its time trend.
In an alternative embodiment, after the target patient (new patient to be treated) is admitted, according to the method for similarly analyzing the disease condition reference based on the special disease view of the present embodiment, similar patients are automatically found and a similar patient pool is formed according to the diagnosis, physical signs, test results, medication and other information of the target patient, a disease condition baseline reference value is obtained according to the similar patients, and changes of disease condition physical signs in the future 24 hours and 3 days are automatically estimated for the disease condition development of the target patient.
As a preferred embodiment, the baseline reference of the disease condition may also change simultaneously, with the change in the input data being based on real-time changes in the target patient as the disease condition progresses. That is, when the disease condition of the target patient progresses, similar patients are searched again from the patient database according to the current (i.e. changed) age, sex, basic physical signs, examination index, diagnosis, medical history, examination result, medication condition, etc. of the target patient. Based on the rolling and iterative search, the accuracy of searching similar patients can be improved, so that the disease development of the target patient can be estimated more accurately.
In other alternative embodiments, with a similar patient pool, the following functions may be implemented: estimating the change trend of the future illness, vital signs, various indexes of blood and the like; analyzing the effectiveness of the current patient treatment regimen according to historical patient treatment effects; estimating quantitative indexes such as patient cost, hospitalization days and the like; estimating risk assessment, such as nosocomial infection, fall pressure sores, venous thrombus delivery, etc.; and evaluating the effect of the treatment scheme.
Example 3
Fig. 3 is a schematic structural diagram of an electronic device provided in this embodiment. The electronic device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the disease condition reference method based on the special disease view similarity analysis of the embodiment 1. The electronic device 30 shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiment of the present invention.
The electronic device 30 may be embodied in the form of a general purpose computing device, which may be, for example, a server device. The components of the electronic device 30 may include, but are not limited to: the at least one processor 31, the at least one memory 32, and a bus 33 connecting the various system components (including the memory 32 and the processor 31).
The bus 33 includes a data bus, an address bus, and a control bus.
The memory 32 may include volatile memory, such as Random Access Memory (RAM)321 and/or cache memory 322, and may further include Read Only Memory (ROM) 323.
The processor 31 executes a computer program stored in the memory 32 to perform various functional applications and data processing, such as a reference method for analyzing a disease condition based on a specific disease view similarity according to embodiment 1 of the present invention.
The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). Such communication may be through input/output (I/O) interfaces 35. Also, model-generating device 30 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via network adapter 36. As shown, network adapter 36 communicates with the other modules of model-generating device 30 via bus 33. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the model-generating device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.
It should be noted that although in the above detailed description several units/modules or sub-units/modules of the electronic device are mentioned, such a division is merely exemplary and not mandatory. Indeed, the features and functionality of two or more of the units/modules described above may be embodied in one unit/module according to embodiments of the invention. Conversely, the features and functions of one unit/module described above may be further divided into embodiments by a plurality of units/modules.
Example 4
The present embodiment provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the steps of the reference method for analyzing a disease condition based on a specific disease view similarity of embodiment 1.
More specific examples, among others, that the readable storage medium may employ may include, but are not limited to: a portable disk, a hard disk, random access memory, read only memory, erasable programmable read only memory, optical storage device, magnetic storage device, or any suitable combination of the foregoing.
In a possible implementation, the invention can also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps of implementing the method for reference of a disease state based on a specific disease view similarity analysis of example 1, when said program product is run on said terminal device.
Where program code for carrying out the invention is written in any combination of one or more programming languages, the program code may be executed entirely on the user device, partly on the user device, as a stand-alone software package, partly on the user device and partly on a remote device or entirely on the remote device.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that this is by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (10)
1. A disease condition reference method based on special disease view similarity analysis is characterized by comprising the following steps:
acquiring similar patients from a patient database according to the index of the target patient to form a similar patient pool;
and acquiring a disease baseline reference value according to the similar patients.
2. The method of claim 1, wherein the step of retrieving similar patients from the patient database based on the target patient comprises:
and obtaining static similar patients according to the static indexes.
3. The reference method for analyzing disease condition based on special disease view similarity as claimed in claim 2, wherein the step of obtaining the statically similar patients according to the static index comprises:
acquiring a first matching degree of the historical patient and the target patient in the patient database, and if the first matching degree is greater than a preset threshold value, setting the historical patient as the static similar patient;
the first matching degree S (X)i，Yj)＝∑kakS(Xik，Yjk)；
Wherein, XiCharacterizing the ith said target patient, YjCharacterizing the jth of said historical patients, S (X)i，Yj) Characterization of XiAnd YjThe first degree of matching; xikThe kth static indicator, Y, characterizing the ith target patientjkThe kth static indicator, S (X), characterizing the jth of said historical patientsik，Yjk) Characterization of XikA second degree of matching of the table; a iskRepresenting the information weight value, sigma, corresponding to the kth static indexkak＝1。
4. The method of claim 3, wherein the static indicators include at least one of age group, diagnosis name, treatment plan.
5. The method of claim 1, wherein the step of retrieving similar patients from the patient database based on the target patient comprises:
and acquiring dynamic similar patients according to the dynamic indexes.
6. The reference method for analyzing disease condition based on special disease view similarity as claimed in claim 5, wherein the obtaining dynamically similar patients according to the dynamic index comprises:
obtaining the dynamic similar patients from historical patients in the patient database according to the reference amount;
wherein the reference amount is:
wherein n is a difference;
and if the reference amount is larger than a preset threshold value, setting the historical patient as the dynamic similar patient.
7. The reference method for analyzing disease condition based on special disease view similarity according to claim 1, wherein the reference value for the disease condition baseline is obtained from at least one of mean, median, mode, and confidence interval of the indices of the similar patients.
8. A disease condition reference system based on special disease view similarity analysis is characterized by comprising a similarity acquisition unit and a baseline acquisition unit;
the similar acquiring unit is used for acquiring similar patients from a patient database according to the indexes of the target patient to form a similar patient pool;
the baseline acquisition unit is used for acquiring a disease baseline reference value according to the similar patients.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program when executed by the processor implements the method for reference of disease condition based on expert view similarity analysis according to any one of claims 1-8.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for reference of a medical condition based on a specific disease view similarity analysis according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011486411.8A CN112652400A (en) | 2020-12-16 | 2020-12-16 | Method, system, device and medium for reference of disease condition based on special disease view similarity analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011486411.8A CN112652400A (en) | 2020-12-16 | 2020-12-16 | Method, system, device and medium for reference of disease condition based on special disease view similarity analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112652400A true CN112652400A (en) | 2021-04-13 |
Family
ID=75354331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011486411.8A Pending CN112652400A (en) | 2020-12-16 | 2020-12-16 | Method, system, device and medium for reference of disease condition based on special disease view similarity analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112652400A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113707308A (en) * | 2021-08-31 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Medical data analysis device and computer readable storage medium |
-
2020
- 2020-12-16 CN CN202011486411.8A patent/CN112652400A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113707308A (en) * | 2021-08-31 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Medical data analysis device and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Juhn et al. | Artificial intelligence approaches using natural language processing to advance EHR-based clinical research | |
| Wang et al. | AI in health: state of the art, challenges, and future directions | |
| US11200968B2 (en) | Verifying medical conditions of patients in electronic medical records | |
| CN107610779B (en) | Disease evaluation and disease risk evaluation method and device | |
| US11881293B2 (en) | Methods for automatic cohort selection in epidemiologic studies and clinical trials | |
| JP6780520B2 (en) | Systems and methods for assessing patient risk using open data and clinician input | |
| CN110136788B (en) | Medical record quality inspection method, device, equipment and storage medium based on automatic detection | |
| KR101555114B1 (en) | A decision-support application and system for problem solving using a question-answering system | |
| Dalianis et al. | HEALTH BANK-A Workbench for Data Science Applications in Healthcare. | |
| JP7304960B2 (en) | Health-informed prognostic score | |
| US7996242B2 (en) | Automatically developing neuropsychiatric treatment plans based on neuroimage data | |
| Lonsdale et al. | Machine learning and artificial intelligence in pediatric research: current state, future prospects, and examples in perioperative and critical care | |
| Tou et al. | Automatic infection detection based on electronic medical records | |
| CN111553478B (en) | Community old people cardiovascular disease prediction system and method based on big data | |
| JP6187474B2 (en) | Medical information analysis program, medical information analysis apparatus, and medical information analysis method | |
| Guo et al. | A disease inference method based on symptom extraction and bidirectional Long Short Term Memory networks | |
| Bulgarelli et al. | Prediction on critically ill patients: the role of “big data” | |
| WO2022081712A1 (en) | Systems and methods for retrieving clinical information based on clinical patient data | |
| Hasan et al. | Understanding current states of machine learning approaches in medical informatics: a systematic literature review | |
| Horng et al. | Consensus development of a modern ontology of emergency department presenting problems—the Hierarchical Presenting Problem Ontology (HaPPy) | |
| Sedghi et al. | Mining clinical text for stroke prediction | |
| JP2021536636A (en) | How to classify medical records | |
| Brown et al. | eQuality: electronic quality assessment from narrative clinical reports | |
| CN112652400A (en) | Method, system, device and medium for reference of disease condition based on special disease view similarity analysis | |
| Cai et al. | RegEMR: a natural language processing system to automatically identify premature ovarian decline from Chinese electronic medical records |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |